PSI: Shared State as the Missing Layer for Coherent AI-Generated Instruments in Personal AI Agents

📅 2026-04-09
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
Current AI-generated personal tools often operate in isolation, lacking coordination and consistency. This work proposes the PSI architecture, which introduces shared state as a foundational system-level primitive to enable automatic integration and cross-tool collaborative reasoning through a unified state bus. The architecture features a shared personal context bus, mechanisms for state publication and write-back, and seamless integration with general-purpose chat agents and graphical user interfaces. Over a three-week autobiographical deployment, the system demonstrated that newly generated tools can automatically connect via a common contract, progressively constructing a coherent, persistent, and interactive personal computing environment.
📝 Abstract
Personal AI tools can now be generated from natural-language requests, but they often remain isolated after creation. We present PSI, a shared-state architecture that turns independently generated modules into coherent instruments: persistent, connected, and chat-complementary artifacts accessible through both GUIs and a generic chat agent. By publishing current state and write-back affordances to a shared personal-context bus, modules enable cross-module reasoning and synchronized actions across interfaces. We study PSI through a three-week autobiographical deployment in a self-developed personal AI environment and show that later-generated instruments can be integrated automatically through the same contract. PSI identifies shared state as the missing systems layer that transforms AI-generated personal software from isolated apps into coherent personal computing environments.
Problem

Research questions and friction points this paper is trying to address.

shared state
personal AI agents
AI-generated instruments
coherent computing environment
isolated modules
Innovation

Methods, ideas, or system contributions that make the work stand out.

shared state
AI-generated instruments
personal AI agents
coherent computing environment
cross-module reasoning